The use of digital images has increased enormously over recent years, however searching and browsing large collections of images efficiently remains a problem. Existing applications allow sorting images by name, date or file size. However images cannot be sorted by their content. Content-based image retrieval (CBIR) systems perform an image search by comparing elementary statistical features of the images. Typical image retrieval systems use low-level features like shape, color or texture, whereas human understanding of an image is considered to be much deeper based on years of acquired knowledge. Due to this "semantic gap" none of these approaches could reach the readiness for marketing until now – mainly because users rate the search results as unsatisfactory. In addition the user has no feedback if all relevant images are found. If no query image is available, the search cannot be performed at all. The freeware ImageSorter takes a different approach. The methods for content based image retrieval are not used for searching but for performing an automatic sorting of huge image collections. The current version of ImageSorter sorts images by the similarity of their color layouts. Future versions of the program will support additional ordering criteria. All images within a folder are sorted in such a way, that similar images are positioned close to each other. This sorting scheme makes it much easier to find a particular image within a huge image set. Naturally also ImageSorter does not understand or recognize image content and cannot distinguish between different people or landscapes. However ImageSorter does not need a query image and is suited to display large sets of up to some thousands images in a visually well organized way that can easily be navigated.