Searching the accident site of a missing airplane is the primary step taken by the search and rescue team before rescuing the victims. However, due to the vast exploration area, lack of technology, no access road, and rough terrain make the search process nontrivial and thus causing much delay in handling the victims. Therefore, this paper aims to develop an automatic wrecked airplane detection system using visual information taken from aerial images such as from a camera. A new deep network is proposed to distinguish robustly the wrecked airplane that has high pose, scale, color variation, and high deformable object. The network leverages the last layers to capture more abstract and semantics information for robust wrecked airplane detection. The network is intertwined by adding more extra layers connected at the end of the layers. To reduce missing detection which is crucial for wrecked airplane detection, an image is then composed into five patches going feed-forwarded to the net in a convolutional manner. Experiments show very well that the proposed method successfully reaches AP=91.87%, and we believe it could bring many benefits for the search and rescue team for accelerating the searching of wrecked airplanes and thus reducing the number of victims.