Classification of intangible cultural heritage (ICH) images is a challenging task due to limited available image data and the high similarity between different classes, making them hard to distinguish. Consequently, traditional machine learning algorithms often achieve low accuracy on such tasks. Our investigation aims at proposing the Bagged CoAtNet (BagCoAtNet) to improve the classification of ICH images. Our BagCoAtNet algorithm learns an ensemble of CoAtNet models, where each CoAtNet is independently trained on a bootstrap sample (sampling with replacement) drawn from the original training image dataset. Each CoAtNet model is trained for a randomly chosen number of epochs, with a randomly selected number of top layers fine-tuned, with its final layer incorporating a random dropout rate. The prediction is determined by majority voting across all CoAtNet models in the ensemble. Empirical test results on the 17-category ICH image dataset demonstrates that our BagCoAtNet algorithm outperforms fine-tuned models like VGG16, DenseNet, CoAtNet, ViT and fusing deep network models. BagCoAtNet achieves a classification accuracy of 71.83%.