One of the main limitations of image search based on
bag-of-features is the memory usage per image. Only a few
million images can be handled on a single machine in rea-
sonable response time. In this paper, we first evaluate how
the memory usage is reduced by using lossless index com-
pression. We then propose an approximate representation
of bag-of-features obtained by projecting the corresponding
histogram onto a set of pre-defined sparse projection func-
tions, producing several image descriptors. Coupled with a
proper indexing structure, an image is represented by a few
hundred bytes. A distance expectation criterion is then used
to rank the images. Our method is at least one order of mag-
nitude faster than standard bag-of-features while providing
excellent search quality.