An image descriptor, multi-channel local oblique symmetry texture pattern (MLOSTP), has been introduced for image retrieval. To capture color, texture, and local spatial information in different channels, three cross-channels, including RV, GV, and BV, are adopted through the combination of RGB with HSV. In each cross-channel, two meaningful local difference maps are introduced between center pixels and surrounding pixels according to their gray differences, which results in more local pixel variations. Based on the maps, two oblique symmetry texture patterns are derived. Not only is the difference between the two color channels explored, but the diagonal asymmetry information of the image is also incorporated into the local patterns. Furthermore, the spatial structure information between different spectral channels is considered. The performance of MLOSTP is estimated by several experiments on four databases. The results show that MLOSTP can achieve better performance than other descriptors.