In this paper, we propose to characterize images without extracting local features, by using global information extracted from the image Bidimensinal Empirical Mode Decomposition (BEMD). This method decompose image into a set of functions named Intrinsic Mode Function (IMF) and residue. The Generalized Gamma Density function (GG) is used to represent the coefficients derived from each IMF, and the Kullback-Leibler Distance (KLD) compute the similarity between GGs. Results are promising: retrieval efficiency is higher than 86 % for same cases.