We propose and implement a novel, robust, and nonparametric test of statistical isotropy of the expansion of the Universe and apply it to around 1000 type Ia supernovae from the Pantheon sample. We calculate the angular clustering of supernova magnitude residuals and compare it to the noise expected under the isotropic assumption. We also test for systematic effects and demonstrate that their effects are negligible or are already accounted for in our procedure. We express our constraints as an upper limit on the rms spatial variation in the Hubble parameter at late times. For the sky smoothed with a Gaussian with FWHM=60°, less than 1% rms spatial variation in the Hubble parameter is allowed at 99.7% confidence.