The main objective of Electronic Support Measure (ESM) is to detect and analyze the threating radar emitters in the surrounding environment. These objectives can be obtained by receiving, measuring, and sorting the intercepted signals, respectively. In the thick of these functions, sorting is absolutely essential. In complex environment, sorting radar pulses is highly problematic, since an enormous number of pulses are received from different emitters in an interleaving form with high noise levels. Conventional sorting techniques have illustrated inefficient results, especially in the presence of modern radar signal such as agility and frequency hopping. In order to ameliorate the sorting performances, we introduce a new sorting algorithm based on similarity and hierarchical clustering techniques, and we denoted it as “Similarity method”. The Similarity method performs magnificent performances without prior knowledge about radars’ emitters, and it is aimed at tackling unconventional circumstances, (i.e. noise pulses, agility signal and hopping frequency). The Similarity method is compared with some existed method, and the simulation results proved its efficiency.