A new techinque for color-based image retrieval is proposed. In this technique, the whole spectrum of a color image is divided into several sub-ranges according to human visual characteristics. Then for each sub-range, the cumulative histogram is used for similarity matching. It is shown that the color contents of image can be well captured by the sub-range cumulative histogram. The new technique has been tested and compared with conventional techniques with the help of a database of 400 images of real flowers, which are quite complicated in color contents. Some satisfactory retrieval results are presented.